کد مقاله | کد نشریه | سال انتشار | مقاله انگلیسی | نسخه تمام متن |
---|---|---|---|---|
5103473 | 1480105 | 2017 | 16 صفحه PDF | دانلود رایگان |
- The proposed function LB_CMK is lower bound on DTW based on square local distance.
- The tightness is better than the existing methods for multivariate time series.
- The efficiency and effectiveness based on LB_CMK is improved for similarity search.
Lower bound function is one of the important techniques used to fast search and index time series data. Multivariate time series has two aspects of high dimensionality including the time-based dimension and the variable-based dimension. Due to the influence of variable-based dimension, a novel method is proposed to deal with the lower bound distance computation for multivariate time series. The proposed method like the traditional ones also reduces the dimensionality of time series in its first step and thus does not directly apply the lower bound function on the multivariate time series. The dimensionality reduction is that multivariate time series is reduced to univariate time series denoted as center sequences according to the principle of piecewise aggregate approximation. In addition, an extended lower bound function is designed to obtain good tightness and fast measure the distance between any two center sequences. The experimental results demonstrate that the proposed lower bound function has better tightness and improves the performance of similarity search in multivariate time series datasets.
Journal: Physica A: Statistical Mechanics and its Applications - Volume 468, 15 February 2017, Pages 622-637